Implicit spatial-frequency fusion of hyperspectral and lidar data via kolmogorov-arnold networks

TL;DR

This paper introduces IFGNet, a novel neural network that adaptively fuses hyperspectral and LiDAR data in spatial and frequency domains using Kolmogorov-Arnold Networks, improving classification accuracy.

Contribution

The paper proposes a new fusion model leveraging Kolmogorov-Arnold Networks with learnable functions and LiDAR-guided implicit aggregation for better hyperspectral-LiDAR integration.

Findings

IFGNet outperforms existing methods on Houston 2013 and MUUFL datasets.

It achieves higher overall accuracy, average accuracy, and Cohen's Kappa.

The architecture maintains efficiency while improving fusion quality.

Abstract

Hyperspectral image (HSI) classification is challenging in complex scenes due to spectral ambiguity, spatial heterogeneity, and the strong coupling between material properties and geometric structures. Although LiDAR provides complementary elevation information, most HSI-LiDAR fusion methods rely on CNNs or MLPs with fixed activation functions and linear weights. These methods struggle to model structural discontinuities in LiDAR data, intricate spectral features of HSI, and their interactions. In addition, fusion of the two modalities in both spatial and frequency domains with LiDAR guidance remains underexplored. To address these issues, we propose the Implicit Frequency-Geometry Fusion Network (IFGNet), which leverages Kolmogorov-Arnold Networks (KANs) with learnable spline-based functions to adaptively capture highly nonlinear relationships between hyperspectral and LiDAR features. Furthermore, IFGNet introduces a LiDAR-guided implicit aggregation module in both spatial and frequency domains, enhancing geometry-aware spatial representations while capturing global structural patterns. Experiments on the Houston 2013 and MUUFL benchmarks demonstrate that IFGNet consistently outperforms existing fusion methods in overall accuracy, average accuracy, and Cohen's Kappa, while maintaining an efficient architecture.